Artificial intelligence and machine vision based method for designing and manufacturing a folding structure for a ship dock

Abstract

The application discloses a kind of based on artificial intelligence and machine vision's dock folding structural member design manufacturing method, system and computer equipment, readable storage medium.It includes: the initial 3D printing model of constructing dock folding structural member;In 3D forming printing process, real-time detection is carried out to printing defect using infrared thermal imaging method, image features of real-time infrared thermal imaging are extracted using convolutional neural network, the image features extracted are detected, different defect types are identified, and the initial printing parameters are adjusted according to the feedback results to obtain target printing parameters;X-ray nondestructive testing is carried out to dock folding structural member, and internal structure defect parameters are obtained;According to internal structure defect parameters, obtain size correction amount, obtain target structure parameters and target 3D printing model.Artificial intelligence and machine vision method is used to efficiently and accurately identify defects and make printing parameter corrections, update target model, and improve product size and performance accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of computer-aided simulation design and additive manufacturing technology, in particular to a ship dock folding structure design and manufacturing method and system based on artificial intelligence and machine vision, a computer device and a computer readable storage medium. BACKGROUND

[0002] With the development of additive manufacturing technology, its application field is more and more widely, and computer-aided simulation design and manufacturing have also been deeply into the design and manufacturing process of various structures. The ship dock folding structure, as an important equipment of marine and ship engineering, plays a vital role in the ship design and manufacturing process. However, in the prior art, the size parameters are generally determined by experience design, and then verified by experimental means. For this, on the one hand, the designed structure model in the prior art cannot be directly used for additive manufacturing and processing. Firstly, for thin-walled and long-suspended rod bases and face base lattices, due to thermal stress and powder support strength, large deformation, collapse, rupture and other failures occur during printing. Secondly, the memory of some lattices is too large, and the software processing capacity is limited, so it is impossible to complete the support setting, slicing and other pre-processing within a reasonable time. In addition, the design means in the prior art is limited, low in efficiency, large in error, poor in product precision and many in defects, which seriously affects the high-quality development of marine and ship engineering. SUMMARY

[0003] In view of the above defects or improvement needs of the prior art, the present application provides a ship dock folding structure design and manufacturing method and system based on artificial intelligence and machine vision, a computer device and a computer readable storage medium. The method of artificial intelligence and machine vision can efficiently and accurately find and identify defects, correct printing parameters, and update the target model to improve the size and performance precision of the product.

[0004] To achieve the above purpose, the present application adopts the following technical solutions.

[0005] In some embodiments, a ship dock folding structure design and manufacturing method based on artificial intelligence and machine vision is provided, which comprises:

[0006] Constructing an initial 3D printing model of the ship dock folding structure, the initial 3D printing model comprising initial structure parameters, the initial structure parameters at least comprising the number of pores and the size of pores;

[0007] According to the initial 3D printing model, 3D forming printing is carried out, which comprises initial printing parameters;

[0008] In the 3D forming printing process, an infrared thermal imaging method is used to detect the printing defects in real time, and the initial printing parameters are adjusted according to the feedback results to obtain target printing parameters;

[0009] 3D printing according to the target printing parameters;

[0010] After the 3D printing according to the target printing parameters is completed, the dock folding structure is subjected to X-ray nondestructive testing, and internal structure defect parameters are obtained;

[0011] According to the internal structure defect parameters, a size correction amount is obtained;

[0012] According to the size correction amount, the initial structure parameters are corrected to obtain target structure parameters and a target 3D printing model, and the target 3D printing model includes the target structure parameters;

[0013] According to the target 3D printing model and the target printing parameters, 3D printing is performed to obtain a dock folding structure;

[0014] In the method, the printing defects are detected in real time by using an infrared thermal imaging method, including: extracting image features of real-time infrared thermal imaging by using a convolutional neural network, and detecting the extracted image features to identify different defect types.

[0015] In some embodiments, the real-time detection of the printing defects by using the infrared thermal imaging method further includes: extracting image features of infrared thermal imaging corresponding to the defects according to the defect positions, and extracting time sequence signals of different defects by using wavelet transform, and analyzing differences in the time sequence signals of different defects, so as to more accurately identify different defect types.

[0016] In some embodiments, the X-ray nondestructive testing of the dock folding structure and the obtaining of internal structure defect parameters include: performing X-ray nondestructive testing on the dock folding structure to obtain X-ray images, and obtaining size parameters of pore defects by using a computer vision image processing method.

[0017] In some embodiments, the initial 3D printing model of the dock folding structure is constructed, including: performing hole shrinking processing on a connecting hole with assembly precision requirements; and performing wall thickness thickening processing on a surface with assembly precision requirements.

[0018] In some embodiments, the wall thickness thickening processing includes increasing the wall thickness of the connecting hole wall by 2-4 mm.

[0019] In some embodiments, the initial 3D printing model of the dock folding structure is constructed, further including: designing at least two orthogonal direction machining references on the outer surface of the model, the machining references being used for machining of assembly sizes and being removed by numerical control machining after 3D printing.

[0020] In some embodiments, the method further comprises: after obtaining the dock folding structure by 3D printing, performing post-processing to obtain a qualified dock folding structure.

[0021] The post-processing at least includes powder bed cleaning, substrate separation, heat treatment, support cleaning, processing assembly size, internal flow channel surface treatment, surface sand blasting, size and surface defect detection.

[0022] In some embodiments, an artificial intelligence and machine vision-based dock folding structure design and manufacturing system is also provided, characterized in that the system comprises:

[0023] An initial 3D printing model construction module is configured to construct an initial 3D printing model of the dock folding structure, wherein the initial 3D printing model comprises initial structure parameters, and the initial structure parameters at least include the number of pores and the size of pores.

[0024] A 3D forming printing module is configured to perform 3D forming printing according to the initial 3D printing model, wherein the 3D forming printing comprises initial printing parameters.

[0025] An artificial intelligence and machine vision module is configured to perform real-time detection of printing defects by using an infrared thermal imaging method during the 3D forming printing, and adjust the initial printing parameters according to the feedback results to obtain target printing parameters.

[0026] The 3D forming printing module is further configured to perform 3D forming printing according to the target printing parameters.

[0027] An X-ray non-destructive testing and computer vision module is configured to perform X-ray non-destructive testing on the dock folding structure after the 3D forming printing according to the target printing parameters is completed, and obtain internal structure defect parameters.

[0028] A size correction module is configured to obtain a size correction amount according to the internal structure defect parameters.

[0029] The size correction module is further configured to correct the initial structure parameters according to the size correction amount to obtain target structure parameters and a target 3D printing model, wherein the target 3D printing model comprises the target structure parameters.

[0030] The 3D forming printing module is further configured to perform 3D printing according to the target 3D printing model and the target printing parameters to obtain a dock folding structure.

[0031] The real-time detection of printing defects by using the infrared thermal imaging method comprises: extracting image features of real-time infrared thermal images by using a convolutional neural network, and detecting the extracted image features to identify different defect types.

[0032] In some embodiments, the real-time detection of printing defects by the infrared thermal imaging method further comprises: extracting image features of infrared thermal images of corresponding defects according to defect positions, and extracting time sequence signals of different defects by wavelet transform, and analyzing differences of the time sequence signals of different defects, so as to more accurately identify different defect types.

[0033] In some embodiments, the X-ray nondestructive testing of the dock folding structural member and obtaining internal structure defect parameters comprises: X-ray nondestructive testing of the dock folding structural member, obtaining X-ray images, and obtaining size parameters of pore defects by computer vision image processing method.

[0034] In some embodiments, an electronic device is further provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method of any one of the preceding embodiments when executing the program.

[0035] In some embodiments, a computer readable storage medium is further provided, wherein the storage medium stores a computer program, and the computer program is executable on a processor to implement the method of any one of the preceding embodiments.

[0036] Compared with the prior art, the present application has the following advantages:

[0037] In some embodiments of the present application, based on artificial intelligence and machine vision, real-time detection of printing defects is performed by an infrared thermal imaging method, image features of real-time infrared thermal images are extracted by a convolutional neural network, the extracted image features are detected, and different defect types are identified. The defect identification during the 3D printing process of the present application can efficiently and accurately find and identify defects, and correct printing parameters. In addition, by X-ray nondestructive testing, internal structure defect parameters are obtained, target model updating is realized, and product size and performance accuracy are improved. BRIEF DESCRIPTION OF DRAWINGS

[0038] Figure 1 The figure is a design and manufacturing method flowchart of a dock folding structural member based on artificial intelligence and machine vision according to an embodiment of the present application.

[0039] Figure 2 The figure is a real-time defect detection schematic diagram based on infrared thermal imaging and machine vision according to an embodiment of the present application.

[0040] Figure 3 The figure is a metal part printing quality evaluation schematic diagram based on X-ray and computer vision according to an embodiment of the present application.

[0041] Figure 4A metal 3D printing process window diagram for an embodiment of the present application.

[0042] Figure 5 A process flow diagram for a post-processing link of a dock folding structural member for an embodiment of the present application.

[0043] Figure 6 An AI and machine vision-based dock folding structural member design and manufacturing system diagram for an embodiment of the present application.

[0044] Figure 7 A schematic diagram of an electronic device for an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0046] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" means that the specific features, structures, materials or characteristics described in combination with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction.

[0047] In the additive forming process using 3D printing, the designed 3D model may not be processed, the main reasons are: first, for thin-walled thick, long suspended rod base, face base lattice, due to thermal stress and powder support strength during printing, large deformation, collapse, rupture and other failures occur; second, the memory of some lattices is too large, the software processing capacity is limited during slicing, and it is impossible to complete the support setting, slicing and other pre-processing within a reasonable time. For the test sample of the extremely small curved surface lattice, the error between the actual printing size and the designed model size is compared, the maximum Z-direction error is 0.368mm, and for the part with thinner wall thickness and larger suspended surface, the size error is larger. The reason for the error is that the measurement point position is a suspended surface, which is supported by the powder below during printing, and the powder softening strength is not enough, resulting in slight collapse.

[0048] To this end, in some embodiments, the size correction can be made based on experience. Specifically, the feasibility of printing each part of the structure is analyzed based on experience and trial printing. For example, in order to prevent the deformation and collapse of the cavity, the horizontal inner cavity with a large diameter is changed to a water droplet-shaped profile. The boss with a height exceeding 0.6 mm on the vertical surface is set to an inclined surface with an inclination angle greater than 45 degrees, which can achieve accurate molding of the local important dimensions.

[0049] In some embodiments, in addition to the adjustment of the size, for some features with high shape retention requirements, the molding accuracy can also be improved by adding removable supports and auxiliary connecting blocks. The supports can be easily removed after printing by machining or manual methods. The auxiliary connecting block is used to improve the shape accuracy. For the "free growth" surface with high accuracy requirements but no mutual constraint during printing, an auxiliary connecting block that can be easily removed by machining can be added between the two plate planes. The auxiliary connecting block plays a role in ensuring the parallelism between the two plates.

[0050] The size modification and addition of auxiliary blocks in the above embodiments are generally completed based on manual experience. In some embodiments of the present application, an AI and machine vision-based dock folding structure design and manufacturing method is also provided, which can adjust the configuration size through multi-modal learning and machine vision methods.

[0051] Figure 1 The overall flowchart of an AI and machine vision-based dock folding structure design and manufacturing method according to an embodiment of the present application is shown in FIG. 1. Referring to FIG. 1, the AI and machine vision-based dock folding structure design and manufacturing method according to an embodiment of the present application includes the following steps. Figure 1 In some embodiments of the present application, an AI and machine vision-based dock folding structure design and manufacturing method is also provided, which includes the following steps.

[0052] An initial 3D printing model of the dock folding structure is constructed, which includes initial structure parameters, and the initial structure parameters at least include the number of pores and the pore size.

[0053] 3D molding printing is performed according to the initial 3D printing model, and the 3D molding printing includes initial printing parameters.

[0054] During the 3D molding printing, an infrared thermal imaging method is used to detect the printing defects in real time, and the initial printing parameters are adjusted according to the feedback results to obtain target printing parameters.

[0055] 3D molding printing is performed according to the target printing parameters.

[0056] After the 3D molding printing according to the target printing parameters is completed, X-ray nondestructive testing is performed on the dock folding structure, and internal structure defect parameters are obtained.

[0057] According to the internal structure defect parameter, a size correction amount is obtained;

[0058] According to the size correction amount, the initial structure parameter is corrected to obtain a target structure parameter and a target 3D printing model, and the target 3D printing model comprises the target structure parameter;

[0059] According to the target 3D printing model and a target printing parameter, 3D printing is performed to obtain a dock folding structure part;

[0060] In the method, the infrared thermal imaging method is used for real-time detection of the printing defects, including: extracting image features of real-time infrared thermal imaging by using a convolutional neural network, and detecting the extracted image features to identify different defect types.

[0061] In the embodiments of the present application, the dock folding structure part can be a dock pier support main body fixed structure, and precise valve bodies and hydraulic elements. The combination of laser process parameters in additive manufacturing largely determines the geometry, local organization, defect size and defect morphology of the melt pool, so the online monitoring technology of additive manufacturing has great significance for the size, performance evaluation and actual application of additive manufacturing products. Non-destructive testing technology, as the current mainstream monitoring technology, has been extended from infrared thermal imaging detection, penetrant detection and eddy current method to ultrasonic detection and X-ray detection. Infrared thermal imaging is sensitive to melt pool surface and internal heat transfer, has the advantages of rapidity, non-contact and can be used for large area detection, but cannot provide information such as melt pool vertical direction morphology and microstructure characteristics. X-ray imaging technology uses X-rays to penetrate objects, analyzes the transmission image to detect internal defects, and is especially suitable for metal printing parts. It can provide high-resolution internal structure images and detect tiny pores.

[0062] In the molding process printing, the embodiments of the present application extract real-time infrared thermal imaging features by using a convolutional neural network, detect the extracted features to identify different defect types, feed back the defect types and defect quantities to the machine position, and the control system adjusts the printing operation and the corresponding printing parameters according to the feedback results.

[0063] Figure 2 A real-time defect detection schematic diagram based on infrared thermal imaging and machine vision combination of an embodiment of the present application is shown in FIG. 1. Figure 2In some embodiments, the real-time detection of printing defects by using the infrared thermal imaging method further comprises: extracting image features of infrared thermal images of corresponding defects according to defect positions, and extracting time sequence signals of different defects by using wavelet transform, and analyzing differences of the time sequence signals of different defects, so as to more accurately identify different defect types. In the embodiments of the application, infrared images of corresponding defects are extracted according to defect positions, and time sequence signals of different defects are extracted by using wavelet transform, and differences of the time sequence signals of different defects are further analyzed and determined, so that different defect types are more accurately identified.

[0064] Figure 3 A schematic diagram of metal part printing quality evaluation based on X-ray and computer vision for an embodiment of the application. Reference is made to Figure 3 In some embodiments, the X-ray nondestructive testing of the folded structure of the dock and obtaining internal structure defect parameters comprise: X-ray nondestructive testing of the folded structure of the dock to obtain X-ray images, and obtaining size parameters of pore defects by using computer vision image processing methods. In the embodiments of the application, after the forming process is printed, the formed metal part is subjected to X-ray nondestructive testing to obtain X-ray images, and size parameters of pore defects of the metal part are obtained by using computer vision image processing methods, and the formed metal part is evaluated for printing quality according to information such as the number and size of pores.

[0065] Figure 4 A schematic diagram of a metal 3D printing process window for an embodiment of the application. Reference is made to Figure 4 By the above real-time defect detection of printing by using infrared images and the defect evaluation of printed parts by using X-ray after printing to evaluate printing quality, a printing process window of the structure and a correction amount of the initial size of the structure can be given, and the size and performance precision of the product are improved.

[0066] In some embodiments, the initial 3D printing model of the folded structure of the dock is constructed, comprising: hole shrinking processing is performed on connecting holes with assembly precision requirements; and wall thickness thickening processing is performed on surfaces with assembly precision requirements.

[0067] Metal additive manufacturing process is essentially a special casting, which is a rapid melting and solidification process of powder under laser high-energy beam irradiation. Therefore, compared with mold pressing and numerical control machining, there is a larger size and shape error. For the connecting size of the hole, groove and other connecting parts on the dock folding structure which needs to be assembled with other components, numerical control machining is needed after printing to ensure the accuracy. However, the surface of the dock folding structure is a continuous shell, and the printing error will cause the wall thickness to be thinned during numerical control machining, thereby reducing the connection strength. During numerical control machining, the dock folding structure has many special features, and there is no ready-made machining reference. In some embodiments, the reference needs to be machined first, which introduces machining error and reduces the thickness of the shell in the reference area.

[0068] For the connecting hole, surface and other connecting parts with assembly accuracy requirements, the hole shrinkage and wall thickness thickening process is performed after the model design is completed. The hole shrinkage is to reduce the diameter of the original larger diameter hole (the minimum diameter is 1 mm). In some embodiments, the wall thickness thickening process includes increasing the wall thickness of the connecting hole wall by 2-4 mm. In the embodiments of the present application, the wall thickness of the connecting hole wall is increased by 2-4 mm. If the wall thickness thickening is less than 2 mm, the printing error of large size will affect the wall thickness. If the thickening is greater than 4 mm, the lightweight effect of the structure will be affected, and the local stiffness of the structure will be changed. In some embodiments, the initial 3D printing model of the dock folding structure is constructed, further comprising: designing at least two orthogonal machining references on the outer surface of the model, the machining references are used for machining of assembly size and surface, and can be removed by numerical control machining after 3D printing.

[0069] The machining reference has a direct impact on the machining accuracy of the assembly size of the 3D printed special-shaped structure. In the embodiments of the present application, at least two orthogonal machining references are designed on the outer surface of the model in advance. The design of the machining reference follows the principles of orthogonality, removability, proximity to important machining size, etc. After the important assembly size is machined, the machining reference can be removed by numerical control machining.

[0070] Figure 5 The process flow diagram of the post-processing link of the dock folding structure of one embodiment of the present application is shown in FIG. 1. Figure 5 In some embodiments, the method further comprises: after 3D printing obtains the dock folding structure, performing post-processing to obtain a qualified dock folding structure.

[0071] The post-processing at least includes powder bed cleaning, substrate separation, heat treatment, support cleaning, machining assembly size, inner flow channel surface treatment, surface sand blasting, size and surface defect detection.

[0072] Specifically, the dock folding structure needs to be post-processed after printing. The post-processing steps include:

[0073] Clearing the powder bed covering the printed part of the powder;

[0074] Separating the workpiece and the 3D printed substrate by wire cutting method, and removing the residual powder in the interior through the powder removal hole with the assistance of high-pressure origin;

[0075] Developing a heat treatment procedure, and sending the workpiece to a large-volume heat treatment furnace for heat treatment according to the procedure;

[0076] Removing the support residues on the surface and in the channel by manual removal, and performing preliminary polishing;

[0077] Processing the required assembly size by machining method;

[0078] Reducing the surface roughness of the internal flow channel by grinding flow grinding and local electrolytic polishing method;

[0079] Carrying out surface sand blasting treatment to further reduce the surface roughness;

[0080] By measuring and non-destructive testing methods, the dimensional accuracy and surface crack defects are inspected to confirm the product qualification.

[0081] Through the above steps of post-processing, the microstructure regulation, thermal stress elimination, assembly size and surface roughness control of the workpiece can be realized, and the qualified product from size to performance can be delivered.

[0082] Figure 6 The figure is a schematic diagram of a ship dock folding structure design and manufacturing system based on artificial intelligence and machine vision according to an embodiment of the present application. Figure 6 In some embodiments of the present application, a ship dock folding structure design and manufacturing system based on artificial intelligence and machine vision is also provided, which comprises:

[0083] An initial 3D printing model construction module is used to construct an initial 3D printing model of the ship dock folding structure, wherein the initial 3D printing model comprises initial structure parameters, and the initial structure parameters at least include the number of pores and the size of pores;

[0084] A 3D forming printing module is used to perform 3D forming printing according to the initial 3D printing model, and the 3D forming printing comprises initial printing parameters;

[0085] An artificial intelligence and machine vision module is used to adopt infrared thermal imaging method to detect the printing defects in real time during the 3D forming printing process, and adjust the initial printing parameters according to the feedback results to obtain target printing parameters;

[0086] The 3D forming printing module is also used to perform 3D forming printing according to the target printing parameters;

[0087] X-ray nondestructive testing and computer vision module, for performing X-ray nondestructive testing on the collapsed structure of the dock after 3D forming printing according to the target printing parameters, and obtaining internal structure defect parameters;

[0088] Size correction module, for obtaining a size correction amount according to the internal structure defect parameters;

[0089] The size correction module is further configured to correct the initial structure parameters according to the size correction amount to obtain target structure parameters and a target 3D printing model, wherein the target 3D printing model comprises the target structure parameters.

[0090] The 3D forming printing module is further configured to perform 3D printing according to the target 3D printing model and target printing parameters to obtain a collapsed structure of a dock.

[0091] In some embodiments, the infrared thermal imaging method for real-time detection of printing defects comprises: extracting image features of real-time infrared thermal images using a convolutional neural network, and detecting the extracted image features to identify different defect types.

[0092] In some embodiments, the infrared thermal imaging method for real-time detection of printing defects further comprises: extracting image features of infrared thermal images corresponding to defects according to defect positions, and extracting time series signals of different defects using wavelet transform to analyze differences in time series signals of different defects, thereby more accurately identifying different defect types.

[0093] In some embodiments, the X-ray nondestructive testing on the collapsed structure of the dock and the obtaining of internal structure defect parameters comprise: performing X-ray nondestructive testing on the collapsed structure of the dock to obtain X-ray images, and obtaining size parameters of pore defects using computer vision image processing methods.

[0094] Reference Figure 7 In some embodiments, an electronic device is also provided, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the numerical simulation, analysis, or control steps in any of the above methods when executing the program.

[0095] At the hardware level, the electronic device comprises a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and of course can also include other hardware required by the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs to implement the above Figure 1The alloy structure optimization design manufacturing method. Of course, in addition to the software implementation, the present specification does not exclude other implementation manners, such as a logic device or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and can also be hardware or a logic device. It can be understood that only the method flow is slightly logically programmed in a hardware description language and programmed into an integrated circuit, and a hardware circuit for implementing the logic method flow can be obtained.

[0096] The above method can be implemented by a controller in any appropriate manner, for example, the controller can take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (for example, software or firmware) executable by the (micro)processor, logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers and embedded microcontrollers, examples of the controller include but are not limited to microcontrollers, the memory controller can also be implemented as part of the control logic of the memory. It can be understood that in addition to implementing the controller in the form of pure computer readable program code, the controller can also be implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers and embedded microcontrollers by logically programming the method steps to achieve the same function. Therefore, such a controller can be considered as a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules for implementing the method and structures within the hardware component.

[0097] The system, device, module or unit in the above embodiment can be implemented by a computer chip or entity, or by a product having certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a game console, a tablet computer, a wearable device or a combination of any of these devices.

[0098] For the convenience of description, the above device is described as various modules respectively described in terms of functions. Of course, in the implementation of the present specification, the functions of each module can be implemented in the same or more software and / or hardware.

[0099] Those skilled in the art will appreciate that embodiments of the application can be supplied as a method, a system, or a computer program product. Accordingly, the present description can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, and the like) embodying computer readable program code.

[0100] The present application is described in reference to the flowchart and / or block diagrams of the methods, apparatus (systems) and computer program products according to embodiments of the present description. It should be understood that each flow and / or block in the flowchart and / or block diagrams, and combinations of flows and / or blocks in the flowchart and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the function specified by the block or blocks.

[0101] In some embodiments, a computer readable storage medium storing a computer program is also provided, the computer program being executed by a processor to implement the method of any of the above.

[0102] In some embodiments, these computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the function specified by the block or blocks.

[0103] In some embodiments, these computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process so that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the function specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more flows and / or blocks ​ means for carrying out the function specified by the block or blocks.

[0104] In some embodiments, the computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0105] In some embodiments, the memory can include non-transitory memory in a computer-readable medium, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash memory, etc. The memory is an example of a computer-readable medium.

[0106] In some embodiments, the computer-readable media includes permanent and non-permanent, removable and non-removable media can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0107] Those skilled in the art will readily understand that the above description is only the preferred embodiment of the present application, and is not intended to limit the present application, and any modification, equivalent replacement and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for designing and manufacturing dock collapse structures based on artificial intelligence and machine vision, characterized in that, The method includes: Construct an initial 3D printed model of the dock folding structure, the initial 3D printed model including initial structural parameters, the initial structural parameters including at least the number of pores and the pore size; Constructing the initial 3D printed model of the dock folding structure includes: shrinking the connecting holes with assembly accuracy requirements; thickening the walls of the surfaces with assembly accuracy requirements; and designing at least two orthogonal machining datums on the outer surface of the model. These machining datums are used for machining assembly dimensions and can be removed by CNC machining after 3D printing. The wall thickness increase process includes increasing the wall thickness of the connecting hole by 2-4 mm; 3D printing is performed based on the initial 3D printing model, and the 3D printing includes initial printing parameters; During the 3D molding and printing process, infrared thermal imaging is used to detect printing defects in real time, and the initial printing parameters are adjusted according to the feedback results to obtain the target printing parameters. Perform 3D molding printing according to the target printing parameters; After 3D printing is completed according to the target printing parameters, the dock folded structure is subjected to X-ray non-destructive testing to obtain internal structural defect parameters. The dimensional correction amount is obtained based on the internal structural defect parameters; Based on the size correction amount, the initial structural parameters are corrected to obtain the target structural parameters and the target 3D printing model, wherein the target 3D printing model includes the target structural parameters; 3D printing is performed based on the target 3D printing model and target printing parameters to obtain a dock folding structure component; Among them, the infrared thermal imaging method is used to detect printing defects in real time, including: using a convolutional neural network to extract real-time infrared thermal imaging image features, detecting the extracted image features, and identifying different defect types; The method of using infrared thermal imaging to detect printing defects in real time also includes: extracting the image features of infrared thermal imaging corresponding to the defect based on the defect location, and using wavelet transform to extract the time series signals of different defects, and analyzing the differences in the time series signals of different defects, so as to more accurately identify different defect types.

2. The method for designing and manufacturing a dock folding structure according to claim 1, characterized in that, The step of performing X-ray non-destructive testing on the collapsed dock structure and obtaining internal structural defect parameters includes: performing X-ray non-destructive testing on the collapsed dock structure, acquiring X-ray images, and using computer vision image processing methods to obtain the size parameters of the pore defects.

3. The method for designing and manufacturing a dock folding structure according to claim 1, characterized in that, The method further includes: after obtaining the dock folding structure component by 3D printing, performing post-processing to obtain a qualified dock folding structure component; The post-processing includes at least powder bed cleaning, substrate separation, heat treatment, support cleaning, machining and assembly dimensions, internal flow channel surface treatment, surface sandblasting, and dimensional and surface defect detection.

4. The method for designing and manufacturing a dock folding structure according to claim 3, characterized in that, Post-processing steps include: Remove the powder covering the printed parts from the toner bed; The workpiece and the 3D printed substrate are separated by wire cutting, and residual powder inside is removed through the powder cleaning hole. Develop heat treatment procedures and send the workpieces to the heat treatment furnace for heat treatment according to the procedures; Preliminary polishing is performed by manually removing any remaining support material from the surface and inside the channels; The required assembly dimensions are achieved through machining methods; The surface roughness of the internal flow channels is reduced by grinding flow milling and local electrolytic polishing. Surface sandblasting is performed to further reduce surface roughness; By using measurement and non-destructive testing methods, the dimensional accuracy and surface crack defects are inspected to confirm the product's qualification.

5. A dock collapse structure design and manufacturing system based on artificial intelligence and machine vision, characterized in that, The system includes: An initial 3D printing model building module is used to build an initial 3D printing model of the dock folding structure. The initial 3D printing model includes initial structural parameters, which include at least the number and size of pores. Constructing the initial 3D printed model of the dock folding structure includes: shrinking the connecting holes with assembly accuracy requirements; thickening the walls of the surfaces with assembly accuracy requirements; and designing at least two orthogonal machining datums on the outer surface of the model. These machining datums are used for machining assembly dimensions and can be removed by CNC machining after 3D printing. The wall thickness increase process includes increasing the wall thickness of the connecting hole by 2-4 mm; A 3D molding and printing module is used to perform 3D molding and printing based on the initial 3D printing model, wherein the 3D molding and printing includes initial printing parameters; The artificial intelligence and machine vision module is used to detect printing defects in real time using infrared thermal imaging during the 3D molding and printing process, and adjust the initial printing parameters according to the feedback results to obtain the target printing parameters. The 3D molding and printing module is also used to perform 3D molding and printing according to the target printing parameters; The X-ray non-destructive testing and computer vision module is used to perform X-ray non-destructive testing on the dock folded structure after 3D molding printing is completed according to the target printing parameters, and to obtain internal structural defect parameters. The size correction module is used to obtain the size correction amount based on the internal structural defect parameters; The size correction module is further configured to correct the initial structural parameters according to the size correction amount to obtain target structural parameters and a target 3D printing model, wherein the target 3D printing model includes the target structural parameters; The 3D molding and printing module is also used to perform 3D printing according to the target 3D printing model and target printing parameters to obtain a dock folding structure component; Among them, the infrared thermal imaging method is used to detect printing defects in real time, including: using a convolutional neural network to extract real-time infrared thermal imaging image features, detecting the extracted image features, and identifying different defect types; The method of using infrared thermal imaging to detect printing defects in real time also includes: extracting the image features of infrared thermal imaging corresponding to the defect based on the defect location, and using wavelet transform to extract the time series signals of different defects, and analyzing the differences in the time series signals of different defects, so as to more accurately identify different defect types.

6. The dock collapse structure design and manufacturing system based on artificial intelligence and machine vision according to claim 5, characterized in that, The step of performing X-ray non-destructive testing on the collapsed dock structure and obtaining internal structural defect parameters includes: performing X-ray non-destructive testing on the collapsed dock structure, acquiring X-ray images, and using computer vision image processing methods to obtain the size parameters of the pore defects.

Images